Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    trading analysis

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Math
    0.60
    فاء
    0.59
    brig
    0.59
    宿
    0.58
    ́
    0.58
    dua
    0.57
     പുതു
    0.57
     Mala
    0.57
    VM
    0.56
    憑
    0.56
    POSITIVE LOGITS
     ignoreString
    0.61
     onları
    0.59
    微笑
    0.58
     illogical
    0.58
     chuckle
    0.57
     repaint
    0.57
     சொல்ல
    0.56
     corriente
    0.55
     grinning
    0.55
     называется
    0.55
    Act Density 0.000%

    No Known Activations